© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75827
    Prev
    Next
    INDEX
    Explanations

    get to know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éu
    -0.81
    dagog
    -0.75
     pensamiento
    -0.74
    ЖА
    -0.74
    調べて
    -0.73
    inear
    -0.72
    жал
    -0.72
    anen
    -0.70
    cba
    -0.69
    퀄
    -0.69
    POSITIVE LOGITS
     know
    3.25
     acquaintance
    2.86
     conocer
    2.64
    认识
    2.63
     kennen
    2.58
     γνω
    2.56
     conhe
    2.55
     acquainted
    2.50
     known
    2.48
    Know
    2.48
    Activations Density 0.037%

    No Known Activations